HOW

Reported on 4 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Image RetrievalonROxford (Medium)
mAP· 2020-07-26
79.4
best: 90.7 (AMES)
SOTA
Learning and aggregating deep local descriptors for instance-level recognition arXiv:2007.13172
Image RetrievalonROxford (Hard)
mAP· 2020-07-26
56.9
best: 80.2 (SuperGlobal)
SOTA
Learning and aggregating deep local descriptors for instance-level recognition arXiv:2007.13172
Image RetrievalonRParis (Medium)
mAP· 2020-07-26
81.6
best: 94.9 (AMES)
Learning and aggregating deep local descriptors for instance-level recognition arXiv:2007.13172
Image RetrievalonRParis (Hard)
mAP· 2020-07-26
62.4
best: 89.7 (AMES)
Learning and aggregating deep local descriptors for instance-level recognition arXiv:2007.13172